问题 MapReduce Application中mapper的数目和分片的数目是一样的
- 默认情况下,分片和输入文件的分块数是相等的。也不完全相等,如果block size大小事128M,文件大小为128.1M,文件的block数目为2,但是application运行过程中,你会发现分片数目是1,而不是2,其中的机理,后面会分析
- 有的程序会设置map的数目,那么map数目是怎样影响分片的数目的呢?
- 如果文件大小为0,是否会作为一个分片传给map任务?
流程
FileInputFormat.getSplits返回文件的分片数目,这部分将介绍其运行流程,后面将粘贴其源码并给出注释
- 通过listStatus()获取输入文件列表files,其中会遍历输入目录的子目录,并过滤掉部分文件,如文件_SUCCESS
- 获取所有的文件大小totalSIze
- goalSIze=totalSize/numMaps。numMaps是用户指定的map数目
- files中取出一个文件file
- 计算splitSize。splitSize=max(minSplitSize,min(file.blockSize,goalSize)),其中minSplitSize是允许的最小分片大小,默认为1B
- 后面根据splitSize大小将file分片。在分片的时候,如果剩余的大小不大于splitSize*1.1,且大于0B的时候,会将该区域整个作为一个分片。这样做是为了防止一个mapper处理的数据太小
- 将file的分片加入到splits中
- 返回4,直到将files遍历完
- 结束,返回splits
源码(hadoop2.2.0)
其实流程算起来也不算复杂,所以就直接用代码注释来做吧
这里边涉及这么几个方法:
1、public List<InputSplit> getSplits(JobContext job), 这个由客户端调用来获得当前Job的所有分片(split),然后发送给JobTracker(新API中应该是ResourceManager),而JobTracker根据这些分片的存储位置来给TaskTracker分配map任务去处理这些分片。这个方法用到了后边的listStatus,然后根据得到的这些文件信息,从FileSystem那里去拉取这些组成这些文件的块的信息(BlockLocation),使用的是getFileBlockLocation(file,start,len),这个方法是与使用的文件系统实现相关的(FileSystem,LocalFileSystem,DistributedFileSystem)
/**
* Generate the list of files and make them into FileSplits.
* @param job the job context
* @throws IOException
*/
public List<InputSplit> getSplits(JobContext job) throws IOException {
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
long maxSize = getMaxSplitSize(job);
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus> files = listStatus(job);
for (FileStatus file: files) {
Path path = file.getPath();
long length = file.getLen();
if (length != 0) {
BlockLocation[] blkLocations;
if (file instanceof LocatedFileStatus) {
blkLocations = ((LocatedFileStatus) file).getBlockLocations();
} else {
FileSystem fs = path.getFileSystem(job.getConfiguration());
blkLocations = fs.getFileBlockLocations(file, 0, length);
}
if (isSplitable(job, path)) {
long blockSize = file.getBlockSize();
long splitSize = computeSplitSize(blockSize, minSize, maxSize);
long bytesRemaining = length;
while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, splitSize,
blkLocations[blkIndex].getHosts()));
bytesRemaining -= splitSize;
}
if (bytesRemaining != 0) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining,
blkLocations[blkIndex].getHosts()));
}
} else { // not splitable
splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts()));
}
} else {
//Create empty hosts array for zero length files
splits.add(makeSplit(path, 0, length, new String[0]));
}
}
// Save the number of input files for metrics/loadgen
job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
LOG.debug("Total # of splits: " + splits.size());
return splits;
}
/**
* Generate the list of files and make them into FileSplits.
* @param job the job context
* @throws IOException
*/
public List<InputSplit> getSplits(JobContext job) throws IOException {
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
long maxSize = getMaxSplitSize(job);
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus> files = listStatus(job);
for (FileStatus file: files) {
Path path = file.getPath();
long length = file.getLen();
if (length != 0) {
BlockLocation[] blkLocations;
if (file instanceof LocatedFileStatus) {
blkLocations = ((LocatedFileStatus) file).getBlockLocations();
} else {
FileSystem fs = path.getFileSystem(job.getConfiguration());
blkLocations = fs.getFileBlockLocations(file, 0, length);
}
if (isSplitable(job, path)) {
long blockSize = file.getBlockSize();
long splitSize = computeSplitSize(blockSize, minSize, maxSize);
long bytesRemaining = length;
while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, splitSize,
blkLocations[blkIndex].getHosts()));
bytesRemaining -= splitSize;
}
if (bytesRemaining != 0) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining,
blkLocations[blkIndex].getHosts()));
}
} else { // not splitable
splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts()));
}
} else {
//Create empty hosts array for zero length files
splits.add(makeSplit(path, 0, length, new String[0]));
}
}
// Save the number of input files for metrics/loadgen
job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
LOG.debug("Total # of splits: " + splits.size());
return splits;
}
2、protected List<FileStatus> listStatus(JobContext job), 先根据“mapred.input.dir”的配置值去得到用户指定的所有Path。然后根据这个JobContext的Configuration得到FileSystem(当然,更可能是 DistributedFileSystem )。最后应用用户可能设置了的PathFilter,通过FileSystem获取所有这些Path所代表的File(FileStatus)。注:这个方法的东西相当多,很多内容还十分陌生。
/** List input directories.
* Subclasses may override to, e.g., select only files matching a regular
* expression.
*
* @param job the job to list input paths for
* @return array of FileStatus objects
* @throws IOException if zero items.
*/
protected List<FileStatus> listStatus(JobContext job
) throws IOException {
List<FileStatus> result = new ArrayList<FileStatus>();
Path[] dirs = getInputPaths(job);
if (dirs.length == 0) {
throw new IOException("No input paths specified in job");
}
// get tokens for all the required FileSystems..
TokenCache.obtainTokensForNamenodes(job.getCredentials(), dirs,
job.getConfiguration());
// Whether we need to recursive look into the directory structure
boolean recursive = getInputDirRecursive(job);
List<IOException> errors = new ArrayList<IOException>();
// creates a MultiPathFilter with the hiddenFileFilter and the
// user provided one (if any).
List<PathFilter> filters = new ArrayList<PathFilter>();
filters.add(hiddenFileFilter);
PathFilter jobFilter = getInputPathFilter(job);
if (jobFilter != null) {
filters.add(jobFilter);
}
PathFilter inputFilter = new MultiPathFilter(filters);
for (int i=0; i < dirs.length; ++i) {
Path p = dirs[i];
FileSystem fs = p.getFileSystem(job.getConfiguration());
FileStatus[] matches = fs.globStatus(p, inputFilter);
if (matches == null) {
errors.add(new IOException("Input path does not exist: " + p));
} else if (matches.length == 0) {
errors.add(new IOException("Input Pattern " + p + " matches 0 files"));
} else {
for (FileStatus globStat: matches) {
if (globStat.isDirectory()) {
RemoteIterator<LocatedFileStatus> iter =
fs.listLocatedStatus(globStat.getPath());
while (iter.hasNext()) {
LocatedFileStatus stat = iter.next();
if (inputFilter.accept(stat.getPath())) {
if (recursive && stat.isDirectory()) {
addInputPathRecursively(result, fs, stat.getPath(),
inputFilter);
} else {
result.add(stat);
}
}
}
} else {
result.add(globStat);
}
}
}
}
if (!errors.isEmpty()) {
throw new InvalidInputException(errors);
}
LOG.info("Total input paths to process : " + result.size());
return result;
}
/** List input directories.
* Subclasses may override to, e.g., select only files matching a regular
* expression.
*
* @param job the job to list input paths for
* @return array of FileStatus objects
* @throws IOException if zero items.
*/
protected List<FileStatus> listStatus(JobContext job
) throws IOException {
List<FileStatus> result = new ArrayList<FileStatus>();
Path[] dirs = getInputPaths(job);
if (dirs.length == 0) {
throw new IOException("No input paths specified in job");
}
// get tokens for all the required FileSystems..
TokenCache.obtainTokensForNamenodes(job.getCredentials(), dirs,
job.getConfiguration());
// Whether we need to recursive look into the directory structure
boolean recursive = getInputDirRecursive(job);
List<IOException> errors = new ArrayList<IOException>();
// creates a MultiPathFilter with the hiddenFileFilter and the
// user provided one (if any).
List<PathFilter> filters = new ArrayList<PathFilter>();
filters.add(hiddenFileFilter);
PathFilter jobFilter = getInputPathFilter(job);
if (jobFilter != null) {
filters.add(jobFilter);
}
PathFilter inputFilter = new MultiPathFilter(filters);
for (int i=0; i < dirs.length; ++i) {
Path p = dirs[i];
FileSystem fs = p.getFileSystem(job.getConfiguration());
FileStatus[] matches = fs.globStatus(p, inputFilter);
if (matches == null) {
errors.add(new IOException("Input path does not exist: " + p));
} else if (matches.length == 0) {
errors.add(new IOException("Input Pattern " + p + " matches 0 files"));
} else {
for (FileStatus globStat: matches) {
if (globStat.isDirectory()) {
RemoteIterator<LocatedFileStatus> iter =
fs.listLocatedStatus(globStat.getPath());
while (iter.hasNext()) {
LocatedFileStatus stat = iter.next();
if (inputFilter.accept(stat.getPath())) {
if (recursive && stat.isDirectory()) {
addInputPathRecursively(result, fs, stat.getPath(),
inputFilter);
} else {
result.add(stat);
}
}
}
} else {
result.add(globStat);
}
}
}
}
if (!errors.isEmpty()) {
throw new InvalidInputException(errors);
}
LOG.info("Total input paths to process : " + result.size());
return result;
}
3、protected long computeSplitSize(long blockSize, long minSize, long maxSize),计算出当前Job所配置的分片最大尺寸。
protected long computeSplitSize(long blockSize, long minSize,
long maxSize) {
return Math.max(minSize, Math.min(maxSize, blockSize));
}
protected long computeSplitSize(long blockSize, long minSize,
long maxSize) {
return Math.max(minSize, Math.min(maxSize, blockSize));
}
4、protected int getBlockIndex(BlockLocation[] blkLocations, long offset), 由于组成文件的块的信息已经获得了,只需要根据offset来计算所在的那个块就行了。
protected int getBlockIndex(BlockLocation[] blkLocations,
long offset) {
for (int i = 0 ; i < blkLocations.length; i++) {
// is the offset inside this block?
if ((blkLocations[i].getOffset() <= offset) &&
(offset < blkLocations[i].getOffset() + blkLocations[i].getLength())){
return i;
}
}
BlockLocation last = blkLocations[blkLocations.length -1];
long fileLength = last.getOffset() + last.getLength() -1;
throw new IllegalArgumentException("Offset " + offset +
" is outside of file (0.." +
fileLength + ")");
}
protected int getBlockIndex(BlockLocation[] blkLocations,
long offset) {
for (int i = 0 ; i < blkLocations.length; i++) {
// is the offset inside this block?
if ((blkLocations[i].getOffset() <= offset) &&
(offset < blkLocations[i].getOffset() + blkLocations[i].getLength())){
return i;
}
}
BlockLocation last = blkLocations[blkLocations.length -1];
long fileLength = last.getOffset() + last.getLength() -1;
throw new IllegalArgumentException("Offset " + offset +
" is outside of file (0.." +
fileLength + ")");
}